From 39b399edceb8bf1afbcda5edcccae3a4e60327c0 Mon Sep 17 00:00:00 2001
From: Kim SangYeon <sy0814k@gmail.com>
Date: Wed, 2 Jan 2019 18:37:56 +0900
Subject: [PATCH] Added RandomPointSelection module

---
 src/mlpack/methods/dbscan/CMakeLists.txt      |  1 +
 src/mlpack/methods/dbscan/dbscan_impl.hpp     |  9 +++---
 src/mlpack/methods/dbscan/dbscan_main.cpp     | 23 +++++++++++---
 .../methods/dbscan/random_point_selection.hpp | 30 ++++++++++++++-----
 4 files changed, 47 insertions(+), 16 deletions(-)

diff --git a/src/mlpack/methods/dbscan/CMakeLists.txt b/src/mlpack/methods/dbscan/CMakeLists.txt
index 70939c9d05..4c5f07ec8f 100644
--- a/src/mlpack/methods/dbscan/CMakeLists.txt
+++ b/src/mlpack/methods/dbscan/CMakeLists.txt
@@ -4,6 +4,7 @@ set(SOURCES
   dbscan.hpp
   dbscan_impl.hpp
   random_point_selection.hpp
+  ordered_point_selection.hpp
 )
 
 # Add directory name to sources.
diff --git a/src/mlpack/methods/dbscan/dbscan_impl.hpp b/src/mlpack/methods/dbscan/dbscan_impl.hpp
index a27784af13..4e9a5073dc 100644
--- a/src/mlpack/methods/dbscan/dbscan_impl.hpp
+++ b/src/mlpack/methods/dbscan/dbscan_impl.hpp
@@ -192,13 +192,14 @@ void DBSCAN<RangeSearchType, PointSelectionPolicy>::BatchCluster(
   // Now loop over all points.
   for (size_t i = 0; i < data.n_cols; ++i)
   {
-    // Union to all neighbors.
-    for (size_t j = 0; j < neighbors[i].size(); ++j)
-      uf.Union(i, neighbors[i][j]);
+    // Get the next index.
+    const size_t index = pointSelector.Select(i, data);
+    for (size_t j = 0; j < neighbors[index].size(); ++j)
+      uf.Union(index, neighbors[index][j]);
   }
 }
 
 } // namespace dbscan
 } // namespace mlpack
 
-#endif
+#endif
\ No newline at end of file
diff --git a/src/mlpack/methods/dbscan/dbscan_main.cpp b/src/mlpack/methods/dbscan/dbscan_main.cpp
index c4afc3c85f..81e43a86dc 100644
--- a/src/mlpack/methods/dbscan/dbscan_main.cpp
+++ b/src/mlpack/methods/dbscan/dbscan_main.cpp
@@ -15,7 +15,7 @@
 #include <mlpack/core/tree/binary_space_tree.hpp>
 #include <mlpack/core/tree/rectangle_tree.hpp>
 #include <mlpack/core/tree/cover_tree.hpp>
-
+#include <mlpack/methods/dbscan/random_point_selection.hpp>
 #include "dbscan.hpp"
 
 using namespace mlpack;
@@ -76,6 +76,8 @@ PARAM_FLAG("single_mode", "If set, single-tree range search (not dual-tree) "
     "will be used.", "S");
 PARAM_FLAG("naive", "If set, brute-force range search (not tree-based) "
     "will be used.", "N");
+PARAM_FLAG("random_selection", "If set, random point selection (not ordered) "
+    "will be used.", "R");
 
 // Actually run the clustering, and process the output.
 template<typename RangeSearchType>
@@ -86,13 +88,26 @@ void RunDBSCAN(RangeSearchType rs = RangeSearchType())
 
   // Load dataset.
   arma::mat dataset = std::move(CLI::GetParam<arma::mat>("input"));
-
+  
   const double epsilon = CLI::GetParam<double>("epsilon");
   const size_t minSize = (size_t) CLI::GetParam<int>("min_size");
 
-  DBSCAN<RangeSearchType> d(epsilon, minSize, !CLI::HasParam("single_mode"),
-      rs);
+  
+  // Check if random selection is used.
+  if (!CLI::HasParam("random_selection"))
+  {
+    DBSCAN<RangeSearchType> d(epsilon, minSize, !CLI::HasParam("single_mode"),
+        rs);   
+  }
+  else
+  {
+    DBSCAN<RangeSearchType, RandomPointSelection> d(epsilon, minSize,
+        !CLI::HasParam("single_mode"), rs);
+  }
 
+  DBSCAN<RangeSearchType, RandomPointSelection> d(epsilon, minSize,
+        !CLI::HasParam("single_mode"), rs);
+  
   // If possible, avoid the overhead of calculating centroids.
   arma::Row<size_t> assignments;
   if (CLI::HasParam("centroids"))
diff --git a/src/mlpack/methods/dbscan/random_point_selection.hpp b/src/mlpack/methods/dbscan/random_point_selection.hpp
index a555830769..1c9ee61605 100644
--- a/src/mlpack/methods/dbscan/random_point_selection.hpp
+++ b/src/mlpack/methods/dbscan/random_point_selection.hpp
@@ -27,16 +27,24 @@ class RandomPointSelection
   /**
    * Select the next point to use, randomly.
    *
-   * @param unvisited Bitset indicating which points are unvisited.
-   * @param data Unused data.
+   * @param point Unused data.
+   * @param data Dataset to cluster.
    */
   template<typename MatType>
-  static size_t Select(const boost::dynamic_bitset<>& unvisited,
-                       const MatType& /* data */)
+  size_t Select(const size_t /* point */,
+                       const MatType& data /* data */)
   {
+    // Initialize the length of the unvisited bitset
+    size_t size = data.n_cols; // Get the size of points.
+    if (unvisited.size() != size) 
+    {
+      unvisited.resize(size); // Resize & Set bitset to one
+      unvisited.set();
+    }
+
     const size_t max = unvisited.count();
     const size_t index = math::RandInt(max);
-
+    
     // Select the index'th unvisited point.
     size_t found = 0;
     for (size_t i = 0; i < unvisited.size(); ++i)
@@ -45,14 +53,20 @@ class RandomPointSelection
         ++found;
 
       if (found > index)
+      {
+        unvisited[i].flip(); // Set unvisited point to visited point
         return i;
+      }
     }
-
     return 0; // Not sure if it is possible to get here.
   }
-};
 
+ private:
+  // Bitmask for unvisited points, If true, mean unvisited.
+  boost::dynamic_bitset<> unvisited;
+};
+  
 } // namespace dbscan
 } // namespace mlpack
 
-#endif
+#endif
\ No newline at end of file